二维多样性保持投影及人脸识别  

Face recognition using two-dimensional diversity preserving projection

作　　者：侯俊[1,2] 郝秀娟[1] 谢德燕[1] 高全学[1] 

机构地区：[1]西安电子科技大学通信工程学院,陕西西安710071 [2]西北工业大学自动化学院,陕西西安710069

出　　处：《西安电子科技大学学报》2012年第6期34-41,共8页Journal of Xidian University

基　　金：国家自然科学基金资助项目(60802075;61271296);ISN国家重点实验室自主资助项目;中央高校基本科研业务费专项资金资助项目;高等学校创新引智计划资助项目(B08038);西北工业大学科技创新基金资助项目(2008KJ02025);陕西省自然科学基础研究计划资助项目(2010JQ8032;2012JM8002)

摘　　要：流形学习有效地保持了数据的局部几何结构,已成为模式识别、机器学习等领域的研究热点.但是它忽略甚至破坏了对模式分析很重要的局部多样性信息,导致局部几何结构描述不够稳定,且性能不是很好.针对此问题,提出了基于图论的多样性保持投影.该方法利用邻接图刻画局部数据之间的变化关系,并给出度量数据多样性大小的差异离散度,然后通过最大化差异离散度提取投影方向.此外,该方法直接从图像矩阵估计差异离散度矩阵,有效地避免了小样本问题.在Yale,UMIST和AR数据库上的实验结果证实了该算法的有效性.Previous work has demonstrated that manifold learning can effectively preserve the local geometry among nearby data,and has become an active topic in pattern recognition and machine learning.However,it ignores or even impairs the local diversity of data,which will impair the recognition accuracy and lead to unstable local geometrical structure representation.In this paper,a novel approach,namely two-dimensional diversity preserving projection（2DDPP）,is proposed for dimensionality reduction.2DDPP constructs an adjacency graph to model the variation of data and measures the variation among nearby data by the diversity scatter,on the basis of which a concise criterion is raised by maximizing the diversity scatter.Moreover,2DDPP directly calculates the diversity scatter matrix from the image matrix,which effectively avoids the small sample size problem.Experiments on Yale,UMIST,and AR databases show the effecitveness of the proposed method.

关 键 词：差异邻接图 流形学习 特征提取 人脸识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]